三维人脸识别算法研究

doi:10.7517/j.issn.1674-0475.2017.02.131

影像科学与光化学 ›› 2017, Vol. 35 ›› Issue (2): 131-139.DOI: 10.7517/j.issn.1674-0475.2017.02.131

三维人脸识别算法研究

胡敏¹, 文永富^1,2

1. 北京理工大学光电学院, 北京 100081;
2. 北京理工大学深圳研究院, 广东深圳 518057

收稿日期:2017-01-25 修回日期:2017-02-21 出版日期:2017-03-15 发布日期:2017-03-15
通讯作者: 文永富
基金资助:
教育部重点实验室2016开放基金项目（2016OEIOF05）和深圳市科技创新项目资助

Research on 3D Face Recognition Methods

HU Min¹, WEN Yongfu^1,2

1. School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, P. R. China;
2. Shenzhen Research Institute, Beijing Institute of Technology, Shenzhen 518057, Guangdong, P. R. China

Received:2017-01-25 Revised:2017-02-21 Online:2017-03-15 Published:2017-03-15

摘要/Abstract

摘要：

近年来，基于三维图像的人脸识别技术已经取得了很大进展，在约束环境下也能获得很好的识别性能，但仍受限于姿态、表情等因素，需要从算法上改进才能解决其影响。本文分别从基于空域直接匹配、基于局部特征匹配和基于整体特征匹配3个角度出发，对人脸匹配算法以及融合算法进行了研究，列出了部分改进算法的实验结果，并分析了算法有效性的原因，总结了目前面临的三维人脸识别算法难以突破的一些困难及未来的研究趋势。

关键词: 三维人脸识别, 特征匹配, 识别算法

Abstract:

The 3D image-based face recognition technology has made great progress in recent years, with good performance achieved under some constrained conditions. However, the technology is still limited by some factors such as facial pose and expression. To solve this kind of impact, the recognition methods must be improved. This paper shares the development status of 3D image face recognition by discussing a series of face matching methods and fuse-improve methods. And separately through three angles:spatial matching methods, local feature based methods and global feature based methods, to state some improvement of 3D face recognition methods. Besides, some experimental results of improved methods are listed and the reasons about effectiveness of the methods are analyzed. Finally, the paper summarizes some challenges which hinder the improvement of 3D face recognition methods, and explore the future research trend.

Key words: 3D face recognition, feature matching, recognition method

胡敏, 文永富. 三维人脸识别算法研究[J]. 影像科学与光化学, 2017, 35(2): 131-139.

HU Min, WEN Yongfu. Research on 3D Face Recognition Methods[J]. Imaging Science and Photochemistry, 2017, 35(2): 131-139.

参考文献

[1] 张敏贵,周德龙,潘泉,张洪才,张绍武.生物特征识别及研究现状[J].生物物理学报,2002,18(2):156. Zhang M G,Zhou D L,Pan Q,Zhang H C,Zhang S W. Biometrics and its situation of present study[J].Acta Biophysica Sinica,2002,18(2):156.
[2] 苏楠,吴冰,徐伟,苏光大. 人脸识别综合技术的发展[J].信息安全研究,2016,2(1):33. Su N,Wu B,Xu W,Su G D. The comprehensive technology development of face recognition[J]. Journal of Information Securyity Research,2016,2(1):33.
[3] Turk M,Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience,1991, 3(1):71-86.
[4] 周杰,卢春雨,张长水,李衍达.人脸自动识别方法综述[J]. 电子学报,2000,28(4):102-106. Zhou J,Lu C Y,Zhang C S,Li Y D. A survey of automatic human face recognition[J]. Acta Electronica Sinica,2000,28(4):102-106.
[5] 张翠平,苏光大.人脸识别技术综述[J]. 中国图像图形学报,2000,5(11):885-894. Zhang C P,Su G D. Human face recognition:a survey[J]. Journal of Image and Graphics,2000,5(11):885-894.
[6] Besl P J,McKay N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992,14(2):239-256.
[7] Lu X G,Colbry D,Jain A K. Three-dimensional model based face recognition[C]. Pattern Recognition, 2004.ICPR 2004. Proceedings of the 17^th International Conference on. IEEE,2004.362-366.
[8] Papatheodorou T,Reuckert D. Evaluation of automatic 4D face recognition using surface and texture registration[C]. Sixth International Conference on Automated Face and Gesture Recognition. IEEE, 2004.321-326.
[9] Huttenloeher D P,Klanderman G A,Rucklidge W J.Comparing images using the Hausdorffdistance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1993, 15(9):850-863.
[10] Achermann B,Bunke H.Classifying range images of human faces with Hausdorff distance[C]. Pattern Recognition, 2000. Proceedings.15^th International Conference on. IEEE,2000.809-813.
[11] Chua C S,Jarvis R. Point signatures:a new representation for 3D object recognition[J].International Journal of Computer Vision, 1997, 25(1):63-85.
[12] Mpiperis I,Malasiotis S,Strintzis M G. 3D face recognition by point signatures and iso-contours[C].Proceedings of the Fourth IASTED International Conference on Signal Processing. IEEE, 2007.328-332.
[13] 徐俊,达飞鹏.一种基于局部描述符的三维人脸识别方法[J]. 模式识别与人工智能,2012,25(1):45-53. Xu J,Da F P. 3D Face Recognition based on local descriptor[J]. Pattern recognition and artificial intelligence,2012,25(1):45-53.
[14] Guo Y L,Lei Y J,Liu L,Wang Y,Bennamoun M,Sohel F.EI3D:expression-invariant 3D face recognition based on feature and shape matching[J]. Pattern Recognition Letters, 2016, 83(3):403-412.
[15] Lei Y J,Feng S Y,Zhou X Z,Guo Y L. An efficient 3D partial face recognition approach with single sample[C]. Industrial Electronics and Applications(ICIEA),2016 IEEE 11^th Conference on. IEEE, 2016.944-999.
[16] Tanaka H T,Ikeda M,Chiaki H. Curvature-based face surface recognition using spherical correlationprincipal directions for curved object recognition[C]. Automatic Face and Gesture Recognition, 1998.Proceedings.Third IEEE International Conference on. IEEE, 1998.372-377.
[17] Gordon G G. Face recognition based on depth and curvature features[C]. Computer Vision and PatternRecognition, 1992.Proceedings CVPR'92., 1992 IEEE Computer Society Conference on. IEEE,1992.108-110.
[18] Moreno A B,Sánchez A,Vélez J F. Face recognition using 3D surface-extracted descriptors[C]. Irish Machine Vision and Image Processing Conference, 2003.2.
[19] 尚常军,丁瑞.基于曲率局部二值模式的深度图像手势特征提取[J]. 计算机应用,2016,36(10):2885-2894. Shang C J,Ding R. Gesture feature extraction of depth image based on curvature and local binary pattern[J]. Journal of Computer Applications,2016,36(10):2885-2894.
[20] Elaiwat S,Bennamoun M,Boussaid F. Acurvelet-based approach for textured 3D face recognition[J]. Pattern Recognition,2015,48(4):1235-1246.
[21] 王跃明,潘纲,吴朝晖. 三维人脸识别研究综述[J]. 计算机辅助设计与图形学学报,2008,20(7):820-827. Wang Y M,Pan G,Wu C H. A survey of 3D face recognition[J]. Journal of Computer-Aided Design & Computer Graphics,2008,20(7):820-827.
[22] Nagamine T,Uemura T,Masuda I. 3D facial image analysis for human identification[C]. Pattern Recognition, 1992. Vol. I. Conference A:Computer Vision and Applications, Proceedings., 11^th IAPR International Conference on. IEEE, 1992.324-327.
[23] Pan G,Wu Z. 3D face recognition from range data[J]. International Journal of Image and Graphics,2005,5(3):573-593.
[24] 李晓娟,杨唐文,阮秋琦,韩建达.基于轮廓线特征的三维人脸识别改进算法[J]. 铁道学报,2012,34(1):34-38. Li X J,Yang T W,Ruan Q Q,Han J D. Modified 3D face recognition algorithm based on contour curve features[J]. Journal of the China Railway Society,2012,34(1):34-38.
[25] 吴昊.基于LBP的三维人脸识别[D]. 长春:吉林大学,2016.27-42. Wu H. 3D face recognition based on LBP[D]. Changchun:Jilin University,2016.27-42.
[26] 刘帅.基于PDE理论的三维人脸重建及识别[D]. 哈尔滨:哈尔滨理工大学,2014.28-51. Liu S. 3D Face Reconstruction and recognition using partial differential equation[D]. Harbin:Harbin University of Science and Technology,2014.28-51.
[27] 詹曙,张芝华,叶长明,蒋建国.三维人脸深度图的流形学习-LOGMAP识别方法[J]. 电子测量与仪器学报,2012,26(2):138-142. Zhan S,Zhang Z H,Ye C M,Jiang J G. 3D facial depth map recognition based on manifold learning-LOGMAP algorithm[J]. Journal of Electronic Measurement and Instrumentation,2012,26(2):138-142.
[28] Lee J C,Milios E. Matching range images of human faces[C]. Computer Vision, 1990. Proceedings, Third International Conference on. IEEE, 1990.722-726.
[29] 刘晓宁,耿国华,王小凤,高原.基于MEGI模型的三维人脸识别方法[J]. 计算机应用研究,2008,25(12):3675-3679. Liu X N,Geng G H,Wang X F,Gao Y. 3D face recognition based on MEGI model[J]. Application Research of Computers,2008,25(12):3675-3679.

三维人脸识别算法研究

Research on 3D Face Recognition Methods

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价